Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 682 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.1013. Min Act: -0.0002

Data Index: 140094 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.1215. Min Act: -0.0001

Data Index: 387549 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.1011. Min Act: -0.0001

Data Index: 800970 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.1011. Min Act: -0.0002

Data Index: 868944 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0942. Min Act: -0.0001

Data Index: 561973 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.1016. Min Act: -0.0001

Data Index: 1080609 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.1072. Min Act: -0.0002

Data Index: 929925 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0955. Min Act: -0.0001

Data Index: 486494 (C4 (Web Text))

Max Activating Token Index: 815

Text #8

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0994. Min Act: -0.0001

Data Index: 155353 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.1001. Min Act: -0.0001

Data Index: 643541 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0887. Min Act: -0.0001

Data Index: 261765 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0853. Min Act: -0.0001

Data Index: 1002195 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0883. Min Act: -0.0002

Data Index: 1309194 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0871. Min Act: -0.0001

Data Index: 594142 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0726. Min Act: -0.0002

Data Index: 1275004 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0895. Min Act: -0.0002

Data Index: 937976 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0859. Min Act: -0.0001

Data Index: 1416779 (Python Code)

Max Activating Token Index: 499

Text #17

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0867. Min Act: -0.0001

Data Index: 276706 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0802. Min Act: -0.0002

Data Index: 133049 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0831. Min Act: -0.0002

Data Index: 1032267 (C4 (Web Text))

Max Activating Token Index: 110